rahul13-13 Goto Github PK

blip

Multi modal architecture for Video-Text matching, Backbone: BLIP, Cross-attention transformer encoder architecture, GPU Parallel processing included

cs50-ai

cs50x

direcformer

[CVPR'22] DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

everything_at_once

This is the official implementation of "Everything at Once - Multi-modal Fusion Transformer for Video Retrieval". CVPR 2022

github-slideshow

A robot powered training repository :robot:

harvard-university-capstone-project-data-science

In this final course in the Harvard University Data Science Professional Certificate, I show what I have learned in the 9 courses by creating TWO long projects and having it assessed by my Professor at Harvard University.

heartratevariabilitytracker

Lucas kanade and DLib 81 for capturing motion in forehead, and cheeks

it-cert-automation-practice

Google IT Automation with Python Professional Certificate - Practice files

journal

Django project.

moment_detr

[NeurIPS 2021] Moment-DETR code and QVHighlights dataset

tps

Action Recognition with divided spatial and temporal Attention Transformer.

video-anomaly

Backbone: ResNext3D-101, Encoder-Decoder Network, t-SNE, PCA

videomatch

xpool

https://layer6ai-labs.github.io/xpool/

yolov7